def output(self, partId, ch_aux): """Uses the student code to compute the output for test cases.""" trainCorpus = HolbrookCorpus('../data/holbrook-tagged-train.dat') if partId in [1,2]: editModel = EditModel('../data/count_1edit.txt', trainCorpus) return json.dumps([[(e.editedWord, e.rule()) for e in editModel.edits(line.strip())] for line in ch_aux.split("\n")]) else: testCorpus = HolbrookCorpus() testCorpus.slurpString(ch_aux) lm = None if partId in [3,4]: lm = LaplaceUnigramLanguageModel(trainCorpus) elif partId in [5,6]: lm = LaplaceBigramLanguageModel(trainCorpus) elif partId in [7,8]: lm = StupidBackoffLanguageModel(trainCorpus) elif partId in [9,10]: lm = CustomLanguageModel(trainCorpus) else: print 'Unknown partId: " + partId' return None speller = SpellCorrect(lm, trainCorpus) output = speller.correctCorpus(testCorpus) # put in the part ID as well output = '[["%d"],%s' % (partId, output[1:]) return output
def output(self, partId, ch_aux): """Uses the student code to compute the output for test cases.""" trainCorpus = HolbrookCorpus('../data/holbrook-tagged-train.dat') if partId in [1, 2]: editModel = EditModel('../data/count_1edit.txt', trainCorpus) return json.dumps([[(e.editedWord, e.rule()) for e in editModel.edits(line.strip())] for line in ch_aux.split("\n")]) else: testCorpus = HolbrookCorpus() testCorpus.slurpString(ch_aux) lm = None if partId in [3, 4]: lm = LaplaceUnigramLanguageModel(trainCorpus) elif partId in [5, 6]: lm = LaplaceBigramLanguageModel(trainCorpus) elif partId in [7, 8]: lm = StupidBackoffLanguageModel(trainCorpus) elif partId in [9, 10]: lm = CustomLanguageModel(trainCorpus) else: print 'Unknown partId: " + partId' return None speller = SpellCorrect(lm, trainCorpus) output = speller.correctCorpus(testCorpus) # put in the part ID as well output = '[["%d"],%s' % (partId, output[1:]) return output